提取近红外光谱有效变量快速检测猪肉挥发性盐基氮  

Rapid Detection of Total Volatile Basic Nitrogen in Pork by Near-Infrared Spectroscopy Using Effective Wavelength Variables

作　　者：刘飞[1] 邹昊[1] 田寒友[1] 汤介兰 刘文营[1] 李家鹏[1] 乔晓玲[1] 

机构地区：[1]中国肉类食品综合研究中心肉类加工技术北京市重点实验室,北京100068 [2]北京中瑞食品有限公司,北京100260

出　　处：《肉类研究》2015年第9期25-29,共5页Meat Research

基　　金：“十二五”国家科技支撑计划项目(2014BAD04B05)

摘　　要：以市售新鲜冷藏(4℃)猪肉为研究对象,采用蒙特卡洛-无信息变量消除算法和连续投影算法对原始近红外光谱的800个波长变量进行提取,共筛选出与挥发性盐基氮含量直接和间接相关的有效波长变量36个,并采用偏最小二乘法构建预测模型,验证集的相关系数和标准偏差分别为0.876 4和1.205 7 mg/100 g。Total volatile basic nitrogen（TVB-N） content is an important reference index for evaluating pork freshness. This study attempted to measure the TVB-N content in pork meat using near infrared spectroscopy with Monte Calo uniformative variable elimination（MCUVE） and successive projections algorithm（SPA）. The results showed that 36 effective wavelength variables directly and indirectly related to the TVB-N content were selected with MCUVE and SPA from the 800 wavelength variables in the original NIR spectra of fresh chilled pork（at 4 ℃）, and the proposed partial least squares（PLS） model had good performance with correlation coefficient of prediction（Rp） of 0.876 4, and standard error of prediction（sEP） of 1.205 7 mg/100 g, respectively.

关 键 词：猪肉 蒙特卡洛-无信息变量消除算法 连续投影算法 挥发性盐基氮 

分 类 号：O657.33[理学—分析化学] TS251.51[理学—化学]